Artificial neural network prediction of the biogas flow rate optimised with an ant colony algorithm. (March 2016)

• Record Type: Journal Article
• Authors: Beltramo, Tetyana; Ranzan, Cassiano; Hinrichs, Joerg; Hitzmann, Bernd
• Is Part Of: Biosystems engineering. Volume 143(2016:Mar.)
• Page Start: 68
• Page End: 78
• Publication Date: 2016-03
• Subjects: Neural network -- Ant Colony Optimisation (ACO) -- Model-driven -- Modelling -- Biogas flow rate; Bioengineering -- Periodicals; Agricultural engineering -- Periodicals; Biological systems -- Periodicals; Génie rural -- Périodiques; Systèmes biologiques -- Périodiques; 631
• DOI: 10.1016/j.biosystemseng.2016.01.006
• Languages: English
• ISSNs: 1537-5110

Abstract

Abstract : The aim of this study was to develop a fast and robust methodology to analyse the biogas production process. The Anaerobic Digestion Model No.1 was used to simulate the co-digestion of agricultural substrates. Neural network models were used to predict the biogas flow rate. With the help of the ant colony optimisation algorithm, the significant process variables were identified. Thus the model dimension was reduced and the model performance was improved. The achieved results showed that the approach gave a reliable way to analyse the biogas production process with respect to the significant process variables. This methodology could be further implemented to control the biogas production process and to manage the substrate composition. Highlights: Simulation of the co-digestion of two agricultural substrates was performed. To predict the biogas flow rate the neural logic was employed. The optimisation was done with the help of metaheuristics, based on variable selection approach.